CloudReg 1.0.1

Automatic terabyte-scale cross-modal brain volume registration

CloudReg

CloudReg is a tool for cross-modal, nonlinear, image registration between arbitrary image volumes.

• Overview
• Documentation
• System Requirements
• Installation Guide
• License
• Issues
• Citing CloudReg

Overview

Quantifying terascale multi-modal human and animal imaging data requires scalable analysis tools. We developed CloudReg, an automated, terascale, cloud-based image analysis pipeline for preprocessing and cross-modal, non-linear registration between volumetric datasets with artifacts. CloudReg was developed using cleared mouse and rat brain light-sheet microscopy images, but is also accurate in registering the following datasets to their respective atlases: in vivo human and ex vivo macaque brain magnetic resonance imaging, ex vivo murine brain micro-computed tomography. Our extensive documentation (below) can enable deployment of this tool for many other datasets/research questions.

Documentation

The official documentation with usage is at https://cloudreg.neurodata.io

Please visit the Run section in the official website for more in depth usage.

System Requirements

Hardware requirements

CloudReg requires only a standard computer with enough RAM to support the in-memory operations since the majority of work is run in cloud services.

Software requirements

OS Requirements

CloudReg is tested on the following OSes and requires Python 3:

• Linux x64
• macOS x64

Installation Guide

Please see Setup on the official website for detailed set up information.

License

This project is covered under the Apache 2.0 License.

Issues

We appreciate detailed bug reports and feature requests (though we appreciate pull requests even more!). Please visit our issues page if you have questions or ideas.

Citing CloudReg

If you find CloudReg useful in your work, please cite the tool via the CloudReg paper

Chandrashekhar, V., Tward, D.J., Crowley, D. et al. CloudReg: automatic terabyte-scale cross-modal brain volume registration. Nat Methods (2021). https://doi.org/10.1038/s41592-021-01218-z